arXiv subjects

Kaiyuan Xu

Publications and source records attributed to Kaiyuan Xu.

14 recordsLinked to original sources

arXiv2026

SurgCUT3R: Surgical Scene-Aware Continuous Understanding of Temporal 3D Representation

Reconstructing surgical scenes from monocular endoscopic video is critical for advancing robotic-assisted surgery. However, the application of state-of-the-art general-purpose reconstruction models is constrained by two key challenges: the lack of supervised training data and performance degradation over long video sequences. To overcome these limitations, we propose SurgCUT3R, a systematic framework that adapts unified 3D reconstruction models to the surgical domain. Our contributions are threefold. First, we develop a data generation pipeline that exploits public stereo surgical datasets to produce large-scale, metric-scale pseudo-ground-truth depth maps, effectively bridging the data gap. Second, we propose a hybrid supervision strategy that couples our pseudo-ground-truth with geometric self-correction to enhance robustness against inherent data imperfections. Third, we introduce a hierarchical inference framework that employs two specialized models to effectively mitigate accumulated pose drift over long surgical videos: one for global stability and one for local accuracy. Experiments on the SCARED and StereoMIS datasets demonstrate that our method achieves a competitive balance between accuracy and efficiency, delivering near state-of-the-art but substantially faster pose estimation and offering a practical and effective solution for robust reconstruction in surgical environments. Project page: https://chumo-xu.github.io/SurgCUT3R-ICRA26/.

cs.CV↗

arXiv2026

Enhancing Fake-News Detection with Node-Level Topological Features

In recent years, the proliferation of misinformation and fake news has posed serious threats to individuals and society, spurring intense research into automated detection methods. Previous work showed that integrating content, user preferences, and propagation structure achieves strong performance, but leaves all graph-level representation learning entirely to the GNN, hiding any explicit topological cues. To close this gap, we introduce a lightweight enhancement: for each node, we append two classical graph-theoretic metrics, degree centrality and local clustering coefficient, to its original BERT and profile embeddings, thus explicitly flagging the roles of hub and community. In the UPFD Politifact subset, this simple modification boosts macro F1 from 0.7753 to 0.8344 over the original baseline. Our study not only demonstrates the practical value of explicit topology features in fake-news detection but also provides an interpretable, easily reproducible template for fusing graph metrics in other information-diffusion tasks.

cs.SI↗

arXiv2025

Generative AI for Urban Planning: Synthesizing Satellite Imagery via Diffusion Models

Generative AI offers new opportunities for automating urban planning by creating site-specific urban layouts and enabling flexible design exploration. However, existing approaches often struggle to produce realistic and practical designs at scale. Therefore, we adapt a state-of-the-art Stable Diffusion model, extended with ControlNet, to generate high-fidelity satellite imagery conditioned on land use descriptions, infrastructure, and natural environments. To overcome data availability limitations, we spatially link satellite imagery with structured land use and constraint information from OpenStreetMap. Using data from three major U.S. cities, we demonstrate that the proposed diffusion model generates realistic and diverse urban landscapes by varying land-use configurations, road networks, and water bodies, facilitating cross-city learning and design diversity. We also systematically evaluate the impacts of varying language prompts and control imagery on the quality of satellite imagery generation. Our model achieves high FID and KID scores and demonstrates robustness across diverse urban contexts. Qualitative assessments from urban planners and the general public show that generated images align closely with design descriptions and constraints, and are often preferred over real images. This work establishes a benchmark for controlled urban imagery generation and highlights the potential of generative AI as a tool for enhancing planning workflows and public engagement.

cs.CV↗

arXiv2024

Optimal Sequencing and Motion Control in a Roundabout with Safety Guarantees

This paper develops a controller for Connected and Automated Vehicles (CAVs) traversing a single-lane roundabout. The controller simultaneously determines the optimal sequence and associated optimal motion control jointly minimizing travel time and energy consumption while providing speed-dependent safety guarantees, as well as satisfying velocity and acceleration constraints. This is achieved by integrating (a) Model Predictive Control (MPC) to enable receding horizon optimization with (b) Control Lyapunov-Barrier Functions (CLBFs) to guarantee convergence to a safe set in finite time, thus providing an extended stability region compared to the use of classic Control Barrier Functions (CBFs). The proposed MPC-CLBF framework addresses both infeasibility and myopic control issues commonly encountered when controlling CAVs over multiple interconnected control zones in a traffic network, which has been a limitation of prior work on CAVs going through roundabouts, while still providing safety guarantees. Simulations under varying traffic demands demonstrate the controller's effectiveness and stability.

eess.SY↗

arXiv2023

Scaling up the Optimal Safe Control of Connected and Automated Vehicles to a Traffic Network: A Hierarchical Framework of Modular Control Zones

We consider the problem of scaling up optimal and safe controllers for Connected and Automated Vehicles (CAVs) from a single Control Zone (CZ) around a traffic conflict area to an entire network. The goal is to jointly minimize travel time and energy consumption for all CAVs, while providing speed-dependent safety guarantees within a CZ and satisfying velocity and acceleration constraints. A hierarchical modular CZ framework is developed consisting of a lower level where decentralized controllers are used that combine Optimal control and Control Barrier Functions (OCBF) and a higher level where a feedback flow controller is proposed to coordinate adjacent CZs. The flow controller is parameterized by a terminal velocity constraint that serves as the interface between CZs. Simulation results show that the proposed modular control zone framework outperforms a direct extension of the OCBF framework to multiple CZs without any flow control.

eess.SY↗

arXiv2022

Attention, Please! Adversarial Defense via Activation Rectification and Preservation

This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are more vulnerable to adversarial attacks; and (2) successful adversarial attacks lead to deviated and scattered attention map. Accordingly, an attention-based adversarial defense framework is designed to simultaneously rectify the attention map for prediction and preserve the attention area between adversarial and original images. The problem of adding iteratively attacked samples is also discussed in the context of visual attention change. We hope the attention-related data analysis and defense solution in this study will shed some light on the mechanism behind the adversarial attack and also facilitate future adversarial defense/attack model design.

cs.CV↗

arXiv2022

Feasibility Guaranteed Traffic Merging Control Using Control Barrier Functions

We consider the merging control problem for Connected and Automated Vehicles (CAVs) aiming to jointly minimize travel time and energy consumption while providing speed-dependent safety guarantees and satisfying velocity and acceleration constraints. Applying the joint optimal control and control barrier function (OCBF) method, a controller that optimally tracks the unconstrained optimal control solution while guaranteeing the satisfaction of all constraints is efficiently obtained by transforming the optimal tracking problem into a sequence of quadratic programs (QPs). However, these QPs can become infeasible, especially under tight control bounds, thus failing to guarantee safety constraints. We solve this problem by deriving a control-dependent feasibility constraint corresponding to each CBF constraint which is added to each QP and we show that each such modified QP is guaranteed to be feasible. Extensive simulations of the merging control problem illustrate the effectiveness of this feasibility guaranteed controller.

eess.SY↗

arXiv2021

PTeacher: a Computer-Aided Personalized Pronunciation Training System with Exaggerated Audio-Visual Corrective Feedback

Second language (L2) English learners often find it difficult to improve their pronunciations due to the lack of expressive and personalized corrective feedback. In this paper, we present Pronunciation Teacher (PTeacher), a Computer-Aided Pronunciation Training (CAPT) system that provides personalized exaggerated audio-visual corrective feedback for mispronunciations. Though the effectiveness of exaggerated feedback has been demonstrated, it is still unclear how to define the appropriate degrees of exaggeration when interacting with individual learners. To fill in this gap, we interview 100 L2 English learners and 22 professional native teachers to understand their needs and experiences. Three critical metrics are proposed for both learners and teachers to identify the best exaggeration levels in both audio and visual modalities. Additionally, we incorporate the personalized dynamic feedback mechanism given the English proficiency of learners. Based on the obtained insights, a comprehensive interactive pronunciation training course is designed to help L2 learners rectify mispronunciations in a more perceptible, understandable, and discriminative manner. Extensive user studies demonstrate that our system significantly promotes the learners' learning efficiency.

cs.HC↗

arXiv2021

Adaptive Adversarial Logits Pairing

Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work that: (1) The inference of adversarially robust model tends to rely on fewer high-contribution features compared with vulnerable ones. (2) The training target of ALP doesn't fit well to a noticeable part of samples, where the logits pairing loss is overemphasized and obstructs minimizing the classification loss. Motivated by these observations, we design an Adaptive Adversarial Logits Pairing (AALP) solution by modifying the training process and training target of ALP. Specifically, AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features, and an adaptive sample weighting module by setting sample-specific training weights to balance between logits pairing loss and classification loss. The proposed AALP solution demonstrates superior defense performance on multiple datasets with extensive experiments.

cs.CV↗

arXiv2021

Decentralized Time and Energy-Optimal Control of Connected and Automated Vehicles in a Roundabout

The paper considers the problem of controlling Connected and Automated Vehicles (CAVs) traveling through a three-entry roundabout so as to jointly minimize both the travel time and the energy consumption while providing speed-dependent safety guarantees, as well as satisfying velocity and acceleration constraints. We first design a systematic approach to dynamically determine the safety constraints and derive the unconstrained optimal control solution. A joint optimal control and barrier function (OCBF) method is then applied to efficiently obtain a controller that optimally track the unconstrained optimal solution while guaranteeing all the constraints. Simulation experiments are performed to compare the optimal controller to a baseline of human-driven vehicles showing effectiveness under symmetric and asymmetric roundabout configurations, balanced and imbalanced traffic rates and different sequencing rules for CAVs.

eess.SY↗

arXiv2020

Comparison of Centralized and Decentralized Approaches in Cooperative Coverage Problems with Energy-Constrained Agents

A multi-agent coverage problem is considered with energy-constrained agents. The objective of this paper is to compare the coverage performance between centralized and decentralized approaches. To this end, a near-optimal centralized coverage control method is developed under energy depletion and repletion constraints. The optimal coverage formation corresponds to the locations of agents where the coverage performance is maximized. The optimal charging formation corresponds to the locations of agents with one agent fixed at the charging station and the remaining agents maximizing the coverage performance. We control the behavior of this cooperative multi-agent system by switching between the optimal coverage formation and the optimal charging formation. Finally, the optimal dwell times at coverage locations, charging time, and agent trajectories are determined so as to maximize coverage over a given time interval. In particular, our controller guarantees that at any time there is at most one agent leaving the team for energy repletion.

math.OC↗

arXiv2020

Butterfly Detection and Classification Based on Integrated YOLO Algorithm

Insects are abundant species on the earth, and the task of identification and identification of insects is complex and arduous. How to apply artificial intelligence technology and digital image processing methods to automatic identification of insect species is a hot issue in current research. In this paper, the problem of automatic detection and classification recognition of butterfly photographs is studied, and a method of bio-labeling suitable for butterfly classification is proposed. On the basis of YOLO algorithm, by synthesizing the results of YOLO models with different training mechanisms, a butterfly automatic detection and classification recognition algorithm based on YOLO algorithm is proposed. It greatly improves the generalization ability of YOLO algorithm and makes it have better ability to solve small sample problems. The experimental results show that the proposed annotation method and integrated YOLO algorithm have high accuracy and recognition rate in butterfly automatic detection and recognition.

cs.CV↗

arXiv2019

blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Turing test was originally proposed to examine whether machine's behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognition-alike questions. The recent development of deep learning has significantly advanced the capability of algorithm in solving CAPTCHA questions, forcing CAPTCHA designers to increase question complexity. Instead of designing questions difficult for both algorithm and human, this study attempts to employ the limitations of algorithm to design robust CAPTCHA questions easily solvable to human. Specifically, our data analysis observes that human and algorithm demonstrates different vulnerability to visual distortions: adversarial perturbation is significantly annoying to algorithm yet friendly to human. We are motivated to employ adversarially perturbed images for robust CAPTCHA design in the context of character-based questions. Three modules of multi-target attack, ensemble adversarial training, and image preprocessing differentiable approximation are proposed to address the characteristics of character-based CAPTCHA cracking. Qualitative and quantitative experimental results demonstrate the effectiveness of the proposed solution. We hope this study can lead to the discussions around adversarial attack/defense in CAPTCHA design and also inspire the future attempts in employing algorithm limitation for practical usage.

cs.CV↗

arXiv2018

Deep neural network based i-vector mapping for speaker verification using short utterances

Text-independent speaker recognition using short utterances is a highly challenging task due to the large variation and content mismatch between short utterances. I-vector based systems have become the standard in speaker verification applications, but they are less effective with short utterances. In this paper, we first compare two state-of-the-art universal background model training methods for i-vector modeling using full-length and short utterance evaluation tasks. The two methods are Gaussian mixture model (GMM) based and deep neural network (DNN) based methods. The results indicate that the I-vector_DNN system outperforms the I-vector_GMM system under various durations. However, the performances of both systems degrade significantly as the duration of the utterances decreases. To address this issue, we propose two novel nonlinear mapping methods which train DNN models to map the i-vectors extracted from short utterances to their corresponding long-utterance i-vectors. The mapped i-vector can restore missing information and reduce the variance of the original short-utterance i-vectors. The proposed methods both model the joint representation of short and long utterance i-vectors by using autoencoder. Experimental results using the NIST SRE 2010 dataset show that both methods provide significant improvement and result in a max of 28.43% relative improvement in Equal Error Rates from a baseline system, when using deep encoder with residual blocks and adding an additional phoneme vector. When further testing the best-validated models of SRE10 on the Speaker In The Wild dataset, the methods result in a 23.12% improvement on arbitrary-duration (1-5 s) short-utterance conditions.

eess.AS↗